Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning
Creators
- 1. University of California, Irvine
Description
Delineating the grounding line of marine-terminating glaciers—where ice starts to become afloat in ocean waters—is crucial for measuring and understanding ice sheet mass balance, glacier dynamics, and their contributions to sea level rise. This task has been previously done using time-consuming, mostly-manual digitizations of differential interferometric synthetic-aperture radar interferograms by human experts. This approach is no longer viable with a fast-growing set of satellite observations and the need to establish time series over entire continents with quantified uncertainties. We present a fully-convolutional neural network with parallel atrous convolutional layers and asymmetric encoder/decoder components that automatically delineates grounding lines at a large scale, efficiently, and accompanied by uncertainty estimates. Our procedure detects grounding lines within 232 m in 100-m posting interferograms, which is comparable to the performance achieved by human experts. We also find value in the machine learning approach in situations that even challenge human experts. We use this approach to map the tidal-induced variability in grounding line position around Antarctica in 22,935 interferograms from year 2018. Along the Getz Ice Shelf, in West Antarctica, we demonstrate that grounding zones are one order magnitude (13.3 ± 3.9) wider than expected from hydrostatic equilibrium, which justifies the need to map grounding lines repeatedly and comprehensively to inform numerical models.
Notes
The grounding lines for the entire Antarctic coastline for available Sentinel1-a/b tracks in 2018 are provided as Shapefiles for the 6-day and 12-day tracks separately, as "AllTracks_6d_GL.shp" and "AllTracks_12d_GL.shp" respectively. The corresponding uncertainty estimates are also provided, as described in the manuscript, which are labelled as "AllTracks_6d_uncertainty.shp" and "AllTracks_12d_uncertainty.shp".
Each grounding line in the Shapefile contains 6 attribudes:
- ID: grounding line ID for each DInSAR scene
- Type: whether the line was used as training or testing data.
- Class: whether each identifined line is a grounding line or a pinning point
- Length: length of the enclosing polygon determining the uncertainty
- Width: width of the enclosing polygon determining the uncertainty
- FILENAME: name of the original shapefile for the grounding line (before all files were combined into one), which gives all relevant information of the DInSAR data, in the format "gl_[Track#]_[YYMMDD scene1]-[YYMMDD scene2]-[YYMMDD scene3]-[YYMMDD scene4]_[Orbit 1]-[Orbit 2]-[Orbit 3]-[Orbit 4]_T[Acquisition time scene1]_[Acquisition time scene 3]_[noise filter length threshold]km.shp".
Disclaimer: while these results provide a complete mapping of the grounding lines for all of Antarctica from available data in 2018, proper interpretation of the results are important for scientific analyses in the presence of any noise in the output of the neural network.
When using this data, please cite the accompanying manuscript along with the data.
For questions, please contact Yara Mohajerani at ymohajer@uci.edu.
Files
ReadME.txt
Files
(1.1 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:0e4bb4efc30ec129e5003a18ea2103cf
|
10 Bytes | Download |
|
md5:b725b2966294601a071d59377a06a0ad
|
7.8 MB | Download |
|
md5:3e573660ca69de460ab57d7400674b28
|
387 Bytes | Download |
|
md5:67ec31480308dcae47b7eb716bbb88bf
|
77.2 MB | Download |
|
md5:5f04acceeaabb2bf7b315d122bad78ba
|
127.1 kB | Download |
|
md5:0e4bb4efc30ec129e5003a18ea2103cf
|
10 Bytes | Download |
|
md5:7b56394b5891af9ecd9c1e990a1045a1
|
7.8 MB | Download |
|
md5:3e573660ca69de460ab57d7400674b28
|
387 Bytes | Download |
|
md5:10cc5052c4ff9ac71c64c6520f7fe88c
|
103.2 MB | Download |
|
md5:6abc06bf550483cead4949033a9da9d7
|
127.0 kB | Download |
|
md5:0e4bb4efc30ec129e5003a18ea2103cf
|
10 Bytes | Download |
|
md5:721a4a091a9e9a7e3e071c568f02d545
|
33.0 MB | Download |
|
md5:3e573660ca69de460ab57d7400674b28
|
387 Bytes | Download |
|
md5:039a9a2c06274f96c712f97e3d2ec9f1
|
371.3 MB | Download |
|
md5:3ca1afdb585bbdcbe5417bbe0d24cb28
|
540.6 kB | Download |
|
md5:0e4bb4efc30ec129e5003a18ea2103cf
|
10 Bytes | Download |
|
md5:6cfccaa39ed0934ec6179eb51b6f4a41
|
33.3 MB | Download |
|
md5:3e573660ca69de460ab57d7400674b28
|
387 Bytes | Download |
|
md5:138ec900de0afe4cccb93825e56afd68
|
492.3 MB | Download |
|
md5:0c81372fd0e6aed9ed365bfed8ecf887
|
540.5 kB | Download |
|
md5:d77a8bd36e65fba56000fd1762d42b0f
|
1.6 kB | Preview Download |
Additional details
Related works
- Is cited by
- https://github.com/yaramohajerani/GL_learning (URL)
- 10.1038/s41598-021-84309-3 (DOI)